Skip to content
This repository was archived by the owner on Apr 27, 2026. It is now read-only.

[WIP] Customizable vertical separators - #138

Open
kba wants to merge 2 commits into
ocropus-archive:masterfrom
kba:customizable-vertical-separators
Open

[WIP] Customizable vertical separators#138
kba wants to merge 2 commits into
ocropus-archive:masterfrom
kba:customizable-vertical-separators

Conversation

@kba

@kba kba commented Nov 4, 2016

Copy link
Copy Markdown
Collaborator

This branch contains the pertinent commits from #68 for now

Comments from that PR:

#68 (comment):

I work a lot with bordered tables and observed damaged characters near the left and right cell borders. I think the vertical separators are expanded too much.

#68 (comment):

That looks useful, but could you please make these values into command line parameters? I'm reluctant to change them because it would require extensive testing to figure out how that affects other page segmentation (since I currently don't have a setup for testing this easily on large datasets).

Something like:

d1 = int(max(5,args.separator_multiplier_h * scale)) + args.sepwiden
seps = minimum(thresh,maximum_filter(grad,(int(args.septhresh_multiplier_h*scale),int(5*scale))))
The defaults should just be 1.0

Eventually, this code will get replaced by trainable 2D LSTM models.

Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants